From: Pavel Begunkov <[email protected]>
To: Jens Axboe <[email protected]>, [email protected]
Subject: [PATCH 01/11] io_uring: don't take ctx refs in task_work handler
Date: Thu, 4 Mar 2021 18:52:15 +0000 [thread overview]
Message-ID: <22cf580b18bfc5481f7ac8f17b2f4a1e7c08e8aa.1614883423.git.asml.silence@gmail.com> (raw)
In-Reply-To: <[email protected]>
__tctx_task_work() guarantees that ctx won't be killed while running
task_works, so we can remove now unnecessary ctx pinning for internally
armed polling.
Signed-off-by: Pavel Begunkov <[email protected]>
---
fs/io_uring.c | 5 -----
1 file changed, 5 deletions(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 3cfc50320923..36d0bc506be4 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -4780,7 +4780,6 @@ static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll,
req->result = mask;
req->task_work.func = func;
- percpu_ref_get(&req->ctx->refs);
/*
* If this fails, then the task is exiting. When a task exits, the
@@ -4877,8 +4876,6 @@ static void io_poll_task_func(struct callback_head *cb)
if (nxt)
__io_req_task_submit(nxt);
}
-
- percpu_ref_put(&ctx->refs);
}
static int io_poll_double_wake(struct wait_queue_entry *wait, unsigned mode,
@@ -4985,7 +4982,6 @@ static void io_async_task_func(struct callback_head *cb)
if (io_poll_rewait(req, &apoll->poll)) {
spin_unlock_irq(&ctx->completion_lock);
- percpu_ref_put(&ctx->refs);
return;
}
@@ -5001,7 +4997,6 @@ static void io_async_task_func(struct callback_head *cb)
else
__io_req_task_cancel(req, -ECANCELED);
- percpu_ref_put(&ctx->refs);
kfree(apoll->double_poll);
kfree(apoll);
}
--
2.24.0
next prev parent reply other threads:[~2021-03-04 18:58 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-03-04 18:52 [PATCH 5.13 00/11] a second batch for 5.13 Pavel Begunkov
2021-03-04 18:52 ` Pavel Begunkov [this message]
2021-03-04 18:52 ` [PATCH 02/11] io_uring: optimise io_uring_enter() Pavel Begunkov
2021-03-04 18:52 ` [PATCH 03/11] io_uring: move setting tctx->sqpoll from hot path Pavel Begunkov
2021-03-04 18:52 ` [PATCH 04/11] io_uring: inline io_clean_op() fast path Pavel Begunkov
2021-03-04 18:52 ` [PATCH 05/11] io_uring: optimise io_dismantle_req() " Pavel Begunkov
2021-03-04 18:52 ` [PATCH 06/11] io_uring: abolish old io_put_file() Pavel Begunkov
2021-03-04 18:52 ` [PATCH 07/11] io_uring: keep io_req_free_batch() call locality Pavel Begunkov
2021-03-04 18:52 ` [PATCH 08/11] io_uring: set req->work closer to all other fields Pavel Begunkov
2021-03-04 18:52 ` [PATCH 09/11] io_uring: inline __io_queue_linked_timeout() Pavel Begunkov
2021-03-04 18:52 ` [PATCH 10/11] io_uring: optimise success case of __io_queue_sqe Pavel Begunkov
2021-03-04 18:52 ` [PATCH 11/11] io_uring: refactor io_flush_cached_reqs() Pavel Begunkov
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=22cf580b18bfc5481f7ac8f17b2f4a1e7c08e8aa.1614883423.git.asml.silence@gmail.com \
[email protected] \
[email protected] \
[email protected] \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox